Abstract: In exemplary embodiments, methods and systems are provided that include: obtaining, via telematics systems of a plurality of vehicles, vehicle telemetry data as the plurality of vehicles travel through one or more geographic regions; transforming, from a computer processor, the vehicle telemetry data into a geohash encoded format pertaining to the one or more geographic regions; identifying, via a processor, a plurality of road junctions using the vehicle telemetry data that is transformed into a geohashed encoding; identifying, via the processor, a plurality of road segments using the vehicle telemetry data that is transformed into a geohashed encoding for the one or more geographic regions; and generating, via the processor, a road network mapping for the one or more geographic regions that includes the plurality of road junctions and the plurality of road segments utilizing the vehicle telemetry data that is transformed into a geohashed encoding.

Abstract: Systems and methods for enhancing anomaly detection using a pattern dictionary are disclosed. An example method includes receiving, from a wearable device, physiological data of the user, and parsing the physiological data into a set of parsed phrases having a number of parsed phrases by applying a pattern dictionary encoder using a pattern dictionary. Each parsed phrase represents a respective subsequence of the physiological data. The example method includes determining a codelength corresponding to the physiological data based on the set of parsed phrases, and comparing (i) the number of parsed phrases to a parsed phrase threshold, and (ii) the codelength to a codelength threshold using an anomaly detection model. Responsive to the number of parsed phrases exceeding the parsed phrase threshold or the codelength exceeding the codelength threshold, the example method includes generating an alert for display on a user interface indicating that the physiological data is anomalous.

Abstract: Computational algorithms integrate and analyze data to consider multiple interdependent, heterogeneous sources and forms of patient data, and using a classification model, provide new learning paradigms, including privileged learning and learning with uncertain clinical data, to determine patient status for conditions such as acute respiratory distress syndrome (ARDS) or non-ARDS.

Abstract: Computational algorithms integrate and analyze data to consider multiple interdependent, heterogeneous sources and forms of patient data, and using a classification model, provide new learning paradigms, including privileged learning and learning with uncertain clinical data, to determine patient status for conditions such as acute respiratory distress syndrome (ARDS) or non-ARDS.